Graph inductive biases in transformers without message passing

Graph inductive biases in transformers without message passing

Pokaži ostale verzije (1)

Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use messag...

Cijeli opis

Bibliografski detalji
Glavni autori: Ma, L, Lin, C, Lim, D, Romero-Soriano, A, Dokania, PK, Coates, M, Torr, PHS, Lim, S-N
Format: Conference item
Jezik:English
Izdano: Proceedings of Machine Learning Research 2023

Slični predmeti